Kapak Resmi

Dependent Task Graph Offloading Model Based on Deep Reinforcement Learning in Mobile Edge Computing

Kaydedildi:
Yayımlandı:Electronics vol. 14, no. 16 (2025), p. 3184-3208
Yazar: Guo Ruxin
Diğer Yazarlar: Zhou Lunyu, Li Linzhi, Song, Yuhui, Xie Xiaolan
Baskı/Yayın Bilgisi:
MDPI AG
Konular:
Scheduling
Integer programming
Deep learning
Edge computing
Applications programs
Graph theory
Optimization techniques
Decision making
Neural networks
Task complexity
Optimization
Mobile computing
Computation offloading
Attention
Algorithms
Methods
Performance evaluation
Heuristic
Workloads
Energy consumption
Markov analysis
Online Erişim:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!
Özet:Mobile edge computing (MEC) has emerged as a promising solution for enabling resource-constrained user devices to run large-scale and complex applications by offloading their computational tasks to the edge servers. One of the most critical challenges in MEC is designing efficient task offloading strategies. Traditional approaches either rely on non-intelligent algorithms that lack adaptability to the dynamic edge environment, or utilize learning-based methods that often ignore task dependencies within applications. To address this issue, this study investigates task offloading for mobile applications with interdependent tasks in an MEC system, employing a deep reinforcement learning framework. Specifically, we model task dependencies using a Directed Acyclic Graph (DAG), where nodes represent subtasks and directed edges indicate their dependency relationships. Based on task priorities, the DAG is transformed into a topological sequence of task vectors. We propose a novel graph-based offloading model, which combines an attention-based network and a Proximal Policy Optimization (PPO) algorithm to learn optimal offloading decisions. Our method leverages offline reinforcement learning through the attention network to capture intrinsic task dependencies within applications. Experimental results show that our proposed model exhibits strong decision-making capabilities and outperforms existing baseline algorithms.
ISSN:2079-9292
DOI:10.3390/electronics14163184
Kaynak:Advanced Technologies & Aerospace Database